24
11

Conditioning of Random Feature Matrices: Double Descent and Generalization Error

Abstract

We provide (high probability) bounds on the condition number of random feature matrices. In particular, we show that if the complexity ratio Nm\frac{N}{m} where NN is the number of neurons and mm is the number of data samples scales like log1(N)\log^{-1}(N) or log(m)\log(m), then the random feature matrix is well-conditioned. This result holds without the need of regularization and relies on establishing various concentration bounds between dependent components of the random feature matrix. Additionally, we derive bounds on the restricted isometry constant of the random feature matrix. We prove that the risk associated with regression problems using a random feature matrix exhibits the double descent phenomenon and that this is an effect of the double descent behavior of the condition number. The risk bounds include the underparameterized setting using the least squares problem and the overparameterized setting where using either the minimum norm interpolation problem or a sparse regression problem. For the least squares or sparse regression cases, we show that the risk decreases as mm and NN increase, even in the presence of bounded or random noise. The risk bound matches the optimal scaling in the literature and the constants in our results are explicit and independent of the dimension of the data.

View on arXiv
Comments on this paper